比较基于机器学习的磁共振成像（MRI）和血液神经退行性生物标志物在预测早期阿尔茨海默病（AD）综合征性转化中的作用。
Comparing machine learning-derived MRI-based and blood-based neurodegeneration biomarkers in predicting syndromal conversion in early AD.
作者信息
Cai Yuan, Fan Xiang, Zhao Lei, Liu Wanting, Luo Yishan, Lau Alexander Yuk Lun, Au Lisa Wing Chi, Shi Lin, Lam Bonnie Y K, Ko Ho, Mok Vincent Chung Tong
机构信息
Lau Tat-chuen Research Centre of Brain Degenerative Diseases in Chinese, Therese Pei Fong Chow Research Centre for Prevention of Dementia, Lui Che Woo Institute of Innovative Medicine, Gerald Choa Neuroscience Institute, Li Ka Shing Institute of Health Science, Division of Neurology, Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong SAR, China.
BrainNow Research Institute, Hong Kong Science and Technology Park, Hong Kong SAR, China.
出版信息
Alzheimers Dement. 2023 Nov;19(11):4987-4998. doi: 10.1002/alz.13083. Epub 2023 Apr 23.
INTRODUCTION
We compared the machine learning-derived, MRI-based Alzheimer's disease (AD) resemblance atrophy index (AD-RAI) with plasma neurofilament light chain (NfL) level in predicting conversion of early AD among cognitively unimpaired (CU) and mild cognitive impairment (MCI) subjects.
METHODS
We recruited participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had the following data: clinical features (age, gender, education, Montreal Cognitive Assessment [MoCA]), structural MRI, plasma biomarkers (p-tau , NfL), cerebrospinal fluid biomarkers (CSF) (Aβ42, p-tau ), and apolipoprotein E (APOE) ε4 genotype. We defined AD using CSF Aβ42 (A+) and p-tau (T+). We defined conversion (C+) if a subject progressed to the next syndromal stage within 4 years.
RESULTS
Of 589 participants, 96 (16.3%) were A+T+C+. AD-RAI performed better than plasma NfL when added on top of clinical features, plasma p-tau , and APOE ε4 genotype (area under the curve [AUC] = 0.832 vs. AUC = 0.650 among CU, AUC = 0.853 vs. AUC = 0.805 among MCI) in predicting A+T+C+.
DISCUSSION
AD-RAI outperformed plasma NfL in predicting syndromal conversion of early AD.
HIGHLIGHTS
AD-RAI outperformed plasma NfL in predicting syndromal conversion among early AD. AD-RAI showed better metrics than volumetric hippocampal measures in predicting syndromal conversion. Combining clinical features, plasma p-tau and apolipoprotein E (APOE) with AD-RAI is the best model for predicting syndromal conversion.
引言
我们比较了基于机器学习的、源自磁共振成像（MRI）的阿尔茨海默病（AD）相似性萎缩指数（AD-RAI）与血浆神经丝轻链（NfL）水平，以预测认知未受损（CU）和轻度认知障碍（MCI）受试者中早期AD的转化情况。
方法
我们从阿尔茨海默病神经影像倡议（ADNI）招募了具有以下数据的参与者：临床特征（年龄、性别、教育程度、蒙特利尔认知评估[MoCA]）、结构MRI、血浆生物标志物（p-tau、NfL）、脑脊液生物标志物（CSF）（Aβ42、p-tau）和载脂蛋白E（APOE）ε4基因型。我们使用脑脊液Aβ42（A+）和p-tau（T+）来定义AD。如果受试者在4年内进展到下一个综合征阶段，我们将其定义为转化（C+）。
结果
在589名参与者中，96名（16.3%）为A+T+C+。在临床特征、血浆p-tau和APOE ε4基因型之上加入AD-RAI时，其在预测A+T+C+方面的表现优于血浆NfL（曲线下面积[AUC]：CU组中分别为0.832和0.650，MCI组中分别为0.853和0.805）。
讨论
在预测早期AD的综合征转化方面，AD-RAI优于血浆NfL。
要点
在预测早期AD的综合征转化方面，AD-RAI优于血浆NfL。在预测综合征转化方面，AD-RAI的指标优于海马体积测量。将临床特征、血浆p-tau和载脂蛋白E（APOE）与AD-RAI相结合是预测综合征转化的最佳模型。
Zotero 插件